perf parse-events: Do not break up AUX event group
Adrian Hunter
reviewerPATCH 1/1 perf parse-events: Do not break up AUX event group
Assume AUX event group is correct and not do break it up.
Example:
Before:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
WARNING: events were regrouped to match PMUs
Cannot add AUX area sampling to a group leaderAfter:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.078 MB perf.data ]
$ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11
sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0
sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0
sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc8350 dl_main+0xa50 => 0 [unknown]
sleep 20444 [003] 7939.510244: 1 branches:uH: 7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0
sleep 20444 [003] 7939.510245: 1 branches:uH: 7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown]
sleep 20444 7939.510245: 10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0
sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0
sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc8862 dl_main+0xf62 => 0 [unknown]
sleep 20444 [003] 7939.510255: 1 branches:uH: 7f5350cc9cdc dl_main+0x23dc => 0 [unknown]
sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc89f6 dl_main+0x10f6 => 7f5350cb9530 _dl_setup_hash+0x0
sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc8a2d dl_main+0x112d => 7f5350cb3990 _dl_new_object+0x0--- tools/perf/util/evsel.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)
tools/perf/util/evsel.c +6 -8
@@ -828,7 +828,11 @@ bool evsel__name_is(struct evsel *evsel, const char *name)const char *evsel__group_pmu_name (const struct evsel *evsel) { -const struct evsel *leader; +const struct evsel *leader =evsel__leader (evsel); + +/* Never break AUX event groups */ +if (evsel__is_aux_event (leader)) +return leader->pmu_name;/* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ if (evsel->pmu_name)
@@ -837,15 +841,9 @@ const char *evsel__group_pmu_name(const struct evsel *evsel)* Software events may be in a group with other uncore PMU events. Use * the pmu_name of the group leader to avoid breaking the software event * out of the group. -* -* Aux event leaders, like intel_pt, expect a group with events from -* other PMUs, so substitute the AUX event's PMU in this case. */ - leader =evsel__leader (evsel); -if ((evsel->core.attr.type ==PERF_TYPE_SOFTWARE ||evsel__is_aux_event (leader)) && - leader->pmu_name) { +if (evsel->core.attr.type ==PERF_TYPE_SOFTWARE && leader->pmu_name)return leader->pmu_name; - }return "cpu" ; }
Signature · 1 line
2.34.1
Ian Rogers
reviewerQuoted 8 lines · Adrian Hunter
Assume AUX event group is correct and not do break it up.
Example:
Before:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1
Could we add this, or similar, to the intel_pt tests?
Quoted 21 lines
WARNING: events were regrouped to match PMUs Cannot add AUX area sampling to a group leader
After:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.078 MB perf.data ] $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc8350 dl_main+0xa50 => 0 [unknown] sleep 20444 [003] 7939.510244: 1 branches:uH: 7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510245: 1 branches:uH: 7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown] sleep 20444 7939.510245: 10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc8862 dl_main+0xf62 => 0 [unknown] sleep 20444 [003] 7939.510255: 1 branches:uH: 7f5350cc9cdc dl_main+0x23dc => 0 [unknown] sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc89f6 dl_main+0x10f6 => 7f5350cb9530 _dl_setup_hash+0x0 sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc8a2d dl_main+0x112d => 7f5350cb3990 _dl_new_object+0x0
Quoted 2 lines
Fixes 347c2f0a0988 ("perf parse-events: Sort and group parsed events")Signed-off-by Adrian Hunter <[email protected]>
These changes are related:
https://lore.kernel.org/lkml/[email protected]/
https://lore.kernel.org/lkml/[email protected]/
Quoted 10 lines
--- tools/perf/util/evsel.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)tools/perf/util/evsel.c +0
-0@@ -828,7 +828,11 @@ bool evsel__name_is(struct evsel *evsel, const char *name)
tools/perf/util/evsel.c bool evsel__name_is(struct evsel *evsel, const char *name) · line 837
Quoted 10 lines
tools/perf/util/evsel.c +5
-1const char *evsel__group_pmu_name (const struct evsel *evsel) { -const struct evsel *leader; +const struct evsel *leader =evsel__leader (evsel); + +/* Never break AUX event groups */ +if (evsel__is_aux_event (leader)) +return leader->pmu_name;/* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */
I think this comment isn't true, hence this patch. I think we should just move the check into the return, so:
return evsel->pmu_name ?: "cpu";
Sorry for the breakage!
Thanks,
Ian
Quoted 21 lines
tools/perf/util/evsel.c +1
-8if (evsel->pmu_name)@@ -837,15 +841,9 @@ const char *evsel__group_pmu_name(const struct evsel *evsel)* Software events may be in a group with other uncore PMU events. Use * the pmu_name of the group leader to avoid breaking the software event * out of the group. -* -* Aux event leaders, like intel_pt, expect a group with events from -* other PMUs, so substitute the AUX event's PMU in this case. */ - leader =evsel__leader (evsel); -if ((evsel->core.attr.type ==PERF_TYPE_SOFTWARE ||evsel__is_aux_event (leader)) && - leader->pmu_name) { +if (evsel->core.attr.type ==PERF_TYPE_SOFTWARE && leader->pmu_name)return leader->pmu_name; - }return "cpu" ; } --2.34.1
Adrian Hunter
reviewerQuoted 11 lines · Ian Rogers
Quoted 8 lines · Adrian Hunter
Assume AUX event group is correct and not do break it up.
Example:
Before:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1Could we add this, or similar, to the
intel_pttests?
Sure
Quoted 22 lines
Quoted 22 lines
WARNING: events were regrouped to match PMUs Cannot add AUX area sampling to a group leader
After:
$ perf record --no-bpf-event -c 10 -e '{intel_pt//,tlb_flush.stlb_any/aux-sample-size=8192/pp}:u' -- sleep 0.1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.078 MB perf.data ] $ perf script -F-dso,+addr | grep -C5 tlb_flush.stlb_any | head -11 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc82a2 dl_main+0x9a2 => 7f5350cb38f0 _dl_add_to_namespace_list+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cb3908 _dl_add_to_namespace_list+0x18 => 7f5350cbb080 rtld_mutex_dummy+0x0 sleep 20444 [003] 7939.510243: 1 branches:uH: 7f5350cc8350 dl_main+0xa50 => 0 [unknown] sleep 20444 [003] 7939.510244: 1 branches:uH: 7f5350cc83ca dl_main+0xaca => 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510245: 1 branches:uH: 7f5350caeb60 _dl_process_pt_gnu_property+0x0 => 0 [unknown] sleep 20444 7939.510245: 10 tlb_flush.stlb_any/aux-sample-size=8192/pp: 0 7f5350caeb60 _dl_process_pt_gnu_property+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc87fe dl_main+0xefe => 7f5350ccd240 strcmp+0x0 sleep 20444 [003] 7939.510254: 1 branches:uH: 7f5350cc8862 dl_main+0xf62 => 0 [unknown] sleep 20444 [003] 7939.510255: 1 branches:uH: 7f5350cc9cdc dl_main+0x23dc => 0 [unknown] sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc89f6 dl_main+0x10f6 => 7f5350cb9530 _dl_setup_hash+0x0 sleep 20444 [003] 7939.510257: 1 branches:uH: 7f5350cc8a2d dl_main+0x112d => 7f5350cb3990 _dl_new_object+0x0
Quoted 6 lines
Quoted 2 lines
Fixes 347c2f0a0988 ("perf parse-events: Sort and group parsed events")Signed-off-by Adrian Hunter <[email protected]>These changes are related:
https://lore.kernel.org/lkml/[email protected]/
https://lore.kernel.org/lkml/[email protected]/
Ok but 347c2f0a0988 is queued for 6.4, so these fixes need to go to 6.4 as well
Quoted 20 lines
Quoted 20 lines
--- tools/perf/util/evsel.c | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-)tools/perf/util/evsel.c +5
-1@@ -828,7 +828,11 @@ bool evsel__name_is(struct evsel *evsel, const char *name)const char *evsel__group_pmu_name (const struct evsel *evsel) { -const struct evsel *leader; +const struct evsel *leader =evsel__leader (evsel); + +/* Never break AUX event groups */ +if (evsel__is_aux_event (leader)) +return leader->pmu_name;
Quoted 5 lines
tools/perf/util/evsel.c bool evsel__name_is(struct evsel *evsel, const char *name) · line 837
Quoted 1 line
tools/perf/util/evsel.c +0
-0/* If the pmu_name is set use it. pmu_name isn't set for CPU and software events. */ I think this comment isn't true, hence this patch. I think we should just move the check into the return, so:
returnevsel->pmu_name?: "cpu";
Ok I will send a V2
Quoted 2 lines
Sorry for the breakage!
No problem!
Quoted 25 lines
Thanks,
IanQuoted 21 lines
tools/perf/util/evsel.c +1
-8if (evsel->pmu_name)@@ -837,15 +841,9 @@ const char *evsel__group_pmu_name(const struct evsel *evsel)* Software events may be in a group with other uncore PMU events. Use * the pmu_name of the group leader to avoid breaking the software event * out of the group. -* -* Aux event leaders, like intel_pt, expect a group with events from -* other PMUs, so substitute the AUX event's PMU in this case. */ - leader =evsel__leader (evsel); -if ((evsel->core.attr.type ==PERF_TYPE_SOFTWARE ||evsel__is_aux_event (leader)) && - leader->pmu_name) { +if (evsel->core.attr.type ==PERF_TYPE_SOFTWARE && leader->pmu_name)return leader->pmu_name; - }return "cpu" ; } --2.34.1